Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 237 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1262531 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1407873 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1160408 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6823. Min Act: 0.0000

Data Index: 447945 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1346262 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1262040 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1349422 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6101. Min Act: -0.0000

Data Index: 239603 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5660. Min Act: -0.0000

Data Index: 68920 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6209. Min Act: -0.0000

Data Index: 643770 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5988. Min Act: -0.0000

Data Index: 980687 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1271988 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5748. Min Act: -0.0000

Data Index: 198047 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5592. Min Act: -0.0000

Data Index: 845470 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1844911 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5131. Min Act: -0.0000

Data Index: 342151 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1820490 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5771. Min Act: -0.0000

Data Index: 827329 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5689. Min Act: -0.0000

Data Index: 515392 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5333. Min Act: -0.0000

Data Index: 61723 (The Pile)

Max Activating Token Index: 373